The effect of fuzzy training targets on voice quality classification

Authors:
Stefan Scherer;John Kane;Christer Gobl;Friedhelm Schwenker
Affiliations:
Institute of Creative Technologies, University of Southern California, United States,Institute of Neural Information Processing, Ulm University, Germany;Phonetics and Speech Laboratory, Trinity College Dublin, Ireland;Phonetics and Speech Laboratory, Trinity College Dublin, Ireland;Institute of Neural Information Processing, Ulm University, Germany
Venue:
MPRSS'12 Proceedings of the First international conference on Multimodal Pattern Recognition of Social Signals in Human-Computer-Interaction
Year:
2012

Citing 6
Cited 0

Glottal wave analysis with Pitch Synchronous Iterative Adaptive Inverse Filtering

Speech Communication - Eurospeech '91
Support vector machines: hype or hallelujah?

ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
Solving Multi-class Pattern Recognition Problems with Tree-Structured Support Vector Machines

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
The role of voice quality in communicating emotion, mood and attitude

Speech Communication - Special issue on speech and emotion
Fuzzy-input fuzzy-output one-against-all support vector machines

KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part III
Fuzzy support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The dynamic use of voice qualities in spoken language can reveal useful information on a speaker's attitude, mood and affective states. This information may be desirable for a range of speech technology applications. However, annotation of voice quality may frequently be inconsistent across raters. But whom should one trust or is the truth somewhere in between? The current study looks first to describe a voice quality feature set that is suitable for differentiating voice qualities on a tense to breathy dimension. These features are used as inputs to a fuzzy-input fuzzy-output support vector machine (F2SVM) algorithm, to automatically classify the voice qualities. The F2SVM is compared to standard approaches and shows promising results. Performances for cross validation, leave one speaker out, and cross corpus experiments of around 90% are achieved.